Three fundamental concepts of the capacity of learning machines

DOI10.1016/0378-4371(93)90558-LzbMATH Open0799.60032OpenAlexW2065847304MaRDI QIDQ1330342FDOQ1330342

Authors: Vladimir Vapnik 

Publication date: 18 July 1994

Published in: Physica A (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0378-4371(93)90558-l

Recommendations

• scientific article; zbMATH DE number 823069
• Some contributions to fixed-distribution learning theory
• scientific article; zbMATH DE number 67636
• scientific article; zbMATH DE number 1081131
• A theory of the learnable

zbMATH Keywords

rate of convergencecapacity of learning machines

Mathematics Subject Classification ID

Limit theorems in probability theory (60F99)

Cites Work

• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz

Cited In (4)

• A tight upper bound on the generalization error of feedforward neural networks
• Maximal relevance and optimal learning machines
• Compactness Hypothesis, Potential Functions, and Rectifying Linear Space in Machine Learning
• LS-SVM approximate solution for affine nonlinear systems with partially unknown functions

This page was built for publication: Three fundamental concepts of the capacity of learning machines

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1330342)